US9934688B2 - Vehicle trajectory determination - Google Patents

Vehicle trajectory determination Download PDF

Info

Publication number
US9934688B2
US9934688B2 US14/814,766 US201514814766A US9934688B2 US 9934688 B2 US9934688 B2 US 9934688B2 US 201514814766 A US201514814766 A US 201514814766A US 9934688 B2 US9934688 B2 US 9934688B2
Authority
US
United States
Prior art keywords
vehicle
policies
policy
vehicles
potential
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active, expires
Application number
US14/814,766
Other languages
English (en)
Other versions
US20170031361A1 (en
Inventor
Edwin Olson
Enric Galceran
Alexander G. Cunningham
Ryan M. EUSTICE
James Robert McBride
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ford Global Technologies LLC
University of Michigan
Original Assignee
Ford Global Technologies LLC
University of Michigan
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Assigned to FORD GLOBAL TECHNOLOGIES, LLC, The Regents of the University of Michigan, Office of Technology Transfer reassignment FORD GLOBAL TECHNOLOGIES, LLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: OLSON, EDWIN, MCBRIDE, JAMES ROBERT, CUNNINGHAM, ALEXANDER G., Galceran, Enric, EUSTICE, Ryan M.
Priority to US14/814,766 priority Critical patent/US9934688B2/en
Application filed by Ford Global Technologies LLC, University of Michigan filed Critical Ford Global Technologies LLC
Assigned to FORD GLOBAL TECHNOLOGIES, LLC reassignment FORD GLOBAL TECHNOLOGIES, LLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: MCBRIDE, JAMES ROBERT
Assigned to THE REGENTS OF THE UNIVERSITY OF MICHIGAN reassignment THE REGENTS OF THE UNIVERSITY OF MICHIGAN CORRECTIVE ASSIGNMENT TO REMOVE THE ASSIGNOR JAMES ROBERT MCBRIDE DATA AND REMOVE THE FIRST RECEIVING PARTY DATA PREVIOUSLY RECORDED AT REEL: 036225 FRAME: 0669. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Assignors: OLSON, EDWIN, CUNNINGHAM, ALEXANDER G., Galceran, Enric, EUSTICE, Ryan M.
Priority to MX2016009489A priority patent/MX365104B/es
Priority to RU2016130094A priority patent/RU2681984C1/ru
Priority to CN201610595858.6A priority patent/CN106428009B/zh
Priority to DE102016113903.3A priority patent/DE102016113903A1/de
Publication of US20170031361A1 publication Critical patent/US20170031361A1/en
Publication of US9934688B2 publication Critical patent/US9934688B2/en
Application granted granted Critical
Active legal-status Critical Current
Adjusted expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/18—Propelling the vehicle
    • B60W30/18009—Propelling the vehicle related to particular drive situations
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B60W40/04—Traffic conditions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/0097—Predicting future conditions
    • G06K9/00791—
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/056—Detecting movement of traffic to be counted or controlled with provision for distinguishing direction of travel
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/161—Decentralised systems, e.g. inter-vehicle communication
    • G08G1/163—Decentralised systems, e.g. inter-vehicle communication involving continuous checking
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0002—Automatic control, details of type of controller or control system architecture
    • B60W2050/0004—In digital systems, e.g. discrete-time systems involving sampling
    • B60W2050/0005—Processor details or data handling, e.g. memory registers or chip architecture
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0019—Control system elements or transfer functions
    • B60W2050/0028—Mathematical models, e.g. for simulation
    • B60W2050/0029—Mathematical model of the driver
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0019—Control system elements or transfer functions
    • B60W2050/0028—Mathematical models, e.g. for simulation
    • B60W2050/0031—Mathematical model of the vehicle
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
    • B60W2050/006—Interpolation; Extrapolation
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0062—Adapting control system settings
    • B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2556/00—Input parameters relating to data
    • B60W2556/10—Historical data
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2556/00—Input parameters relating to data
    • B60W2556/45—External transmission of data to or from the vehicle
    • B60W2556/50—External transmission of data to or from the vehicle of positioning data, e.g. GPS [Global Positioning System] data
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2556/00—Input parameters relating to data
    • B60W2556/45—External transmission of data to or from the vehicle
    • B60W2556/65—Data transmitted between vehicles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle

Definitions

  • An autonomous vehicle must evaluate consequences of potential actions by anticipating uncertain intentions of other traffic participants, e.g., vehicles. Future actions of the other traffic participants depend on planned trajectories governing their behavior which are generally unknown, and additionally depend on interactions between the participants. Simply extrapolating paths of other vehicles may not give an indication of their intentions for future actions.
  • FIG. 1 is a diagram of an exemplary traffic environment.
  • FIG. 2 is a block diagram of an autonomous driving system including multipolicy decision-making.
  • FIG. 3 is a diagram illustrating segmentation of driving history of a participant in a traffic environment.
  • FIG. 4 is a diagram of an exemplary process for controlling a vehicle using multipolicy decision-making.
  • a multipolicy decision-making system advantageously uses information about the trajectory of other, non-host vehicles to determine a planned trajectory for a host vehicle.
  • the system receives data describing the recent trajectory of each of the non-host vehicles, and identifies segments within the respective trajectories that may be explained by a policy from a discrete set of pre-defined policies.
  • policy means a set of one or more rules to determine a trajectory of a vehicle. More specifically, “policy” represents an intention with respect to the vehicle trajectory at a moment in time. Examples of policies are provided in detail below, and include maintaining or changing lanes, emergency stop, overtaking a non-host vehicle, etc.
  • the multipolicy decision-making system Based on the segmentation of the respective trajectories, the multipolicy decision-making system identifies distributions of likely policies governing future trajectories of each of the non-host vehicles. Based on these distributions, the multipolicy decision-making system further identifies one or more candidate policies to determine the trajectory of the host vehicle.
  • the multipolicy decision-making system selects sample policies for each of the vehicles, forward-simulates the traffic environment over a time horizon, and compares the results with an established set of rewards.
  • the process repeats iteratively to identify and adjust the policy to determine the trajectory of the host vehicle. Utilizing a discrete set of pre-defined policies to categorize the operation of a vehicle advantageously reduces the complexity of simulating the interaction of vehicles within the traffic environment.
  • Multipolicy decision-making for vehicles is founded on a generalized process for decision-making applicable to dynamic, uncertain environments that are characterized by highly interactive coupling between participants, as disclosed herein.
  • V denote a set of vehicles interacting in a local neighborhood, e.g., within a predetermined distance such as 250 meters, of a host vehicle, including the host vehicle itself.
  • a vehicle v ⁇ V can take an action a t v ⁇ A v to transition from state x t v ⁇ x v to x t+1 v .
  • a non-zero is a tuple of the pose, velocity, and acceleration
  • an action a t v is a tuple of controls for steering, throttle, brake, shifter, and directionals.
  • Pose may include a position of a vehicle and the orientation (roll, pitch, yaw).
  • Pose may further include one or more of velocity, acceleration and rotation rate.
  • the shifter may include a transmission, and may include one or more states, e.g., drive, park, and reverse.
  • Directionals may include signals indicating future intentions, e.g., turn signals.
  • x t include all state variables x t v for all vehicles at time t, and similarly let a t ⁇ A be the actions of all vehicles.
  • an observation z t v is a tuple including the estimated poses and velocities of nearby vehicles and a location of static obstacles.
  • a policy is a mapping ⁇ : X ⁇ Z v ⁇ A v that yields an action from the current maximum a posteriori (MAP) estimate of the state and an observation:
  • R(x t ) is a real-valued reward function R:X ⁇ R.
  • the evolution of p(x t ) over time is governed by
  • the decision horizon H may be, e.g., a predetermined time, such as 30 seconds. Alternatively, the decision horizon H may be determined, e.g., based on a type of traffic situation, such as, approaching an intersection, driving on a highway, etc. Other factors, such as environmental factors may also be considered in determining the decision horizon H.
  • the driver model D (x t ,z t v ,a t v ) implicitly assumes that instantaneous actions of each vehicle are independent of each other, because a t v is conditioned only on x t and z t v .
  • Instantaneous actions may be defined as actions chosen by each of the vehicles at a given timestep that are independent of knowledge of other vehicle's actions. Modeled agents can, however, still react to the observed states of nearby vehicles via z t v . That is to say, that vehicles do not collaborate with each other, as would be implied by an action a t v dependent on a t .
  • x t v ,z t v ) p ( x t v ), (3) and the independence assumption finally leads to p ( x t+1 ) ⁇ v ⁇ V ⁇ x v z v A v p v ( x t v ,x t+1 v ,z t v ,a t v ) da t v dz t v dx t v v . (4)
  • the traffic environment 10 includes a highway 12 , a host vehicle 14 , a first non-host vehicle 16 a and second non-host vehicle 16 b .
  • the host vehicle 14 is a vehicle programmed to use multipolicy decision-making for at least some driving decisions.
  • Non-host vehicles 16 are vehicles other than the host vehicle 14 . It is to be understood that the statement herein that a “vehicle is programmed” means that a vehicle includes a computer that is programmed as described, e.g., a computer 20 as discussed below.
  • the host vehicle 14 is programmed to define a traffic environment 10 which includes the host vehicle 14 and one or more non-host vehicles 16 within a predefined distance to the host vehicle 14 .
  • the predefined distance to the host vehicle 14 may be defined, e.g., as within a first fixed distance in a first specified direction, e.g., 20 meters of a left or right side of the host vehicle 14 and within a second fixed distance in a second specified direction, e.g., 100 meters of a front or rear of the host vehicle 14 .
  • the determination of “the predefined distance” may additionally or alternatively be dependent on a particular traffic situation.
  • a smaller area may be considered as within the predefined distance to the host vehicle 14 in a parking situation, and a larger area may be considered as within the predefined distance to the host vehicle 14 on a highway.
  • the predefined distance to the host vehicle 14 may be defined to depend on other conditions, e.g., a speed of the host vehicle 14 , weather conditions, light conditions (day or night), etc.
  • the host vehicle 14 is further programmed to collect data regarding recent driving history of each of the one or more non-host vehicles 16 and to perform a change-point analysis on each of the non-host vehicle 16 driving histories.
  • the host vehicle 14 divides the recent driving history of each of the non-host vehicles 16 into segments and identifies a distribution of likely polices 46 ( FIG. 2 ), e.g., driving along a lane, turning at an intersection, etc. which governed the non-host vehicle 16 during each of the segments.
  • the host vehicle 14 is further programmed to determine one or more policies 46 to govern its behavior.
  • One or more closed-loop simulations of the traffic environment 10 are performed based on samples from the policy 46 distributions of the other vehicles 16 and the host vehicle 14 .
  • a merging non-host vehicle 16 may accelerate, and the host vehicle 14 may slow down to make room for it.
  • the results of the simulations are compared to a reward function, i.e., a set of desired outcomes for the traffic environment 10 .
  • the host vehicle 14 is further programmed to decide upon a policy 46 to govern driving behavior at a current timestep.
  • a timestep may be defined as a period of time between consecutive updates of a policy to govern the host vehicle.
  • the timestep for the multipolicy decision-making system may be periodic, e.g., in a range from one to four Hertz. In this manner, the host vehicle 14 may make iterative driving decisions based on coupled interactions with the non-host vehicles 16 .
  • the vehicle 14 may detect anomalous behavior of one or more other vehicles 16 that cannot be explained by the set of policies 46 available to the environment 10 , e.g., driving the wrong direction on a highway, driving erratically, etc.
  • a single policy accounting for only the current state and map of the environment may be selected to model the non-host vehicle 16 exhibiting the anomalous behavior.
  • multipolicy decision-making may be suspended when a non-host vehicle 16 exhibiting anomalous behavior is detected, and an alternate form of driving decision-making, may be employed.
  • the host vehicle 14 programmed to use multipolicy decision-making to make driving decisions is shown in FIG. 2 .
  • the host vehicle includes a computer 20 , a user interface 22 , one or more data collectors 24 , a road network definition file (RNFD) 25 , and one or more controllers 26 .
  • the host vehicle 14 is generally a land-based vehicle having three or more wheels, e.g., a passenger vehicle, light truck, etc.
  • the host vehicle 14 has a front, a rear, a left side and a right side, wherein the terms front, rear, left and right are understood from the perspective of an operator of the host vehicle 14 seated in a driver's seat in a standard operating position, i.e., facing a steering wheel.
  • the computer 20 generally includes a processor and a memory, the memory including one or more forms of computer-readable media, and storing instructions executable by the processor for performing various operations, including as disclosed herein. Further, the computer 20 may include and/or be communicatively coupled to one or more other computing devices included in the host vehicle 14 for monitoring and/or controlling various vehicle components.
  • the computer 20 is generally programmed and arranged for communications on a controller area network (CAN) bus or the like.
  • CAN controller area network
  • the computer 20 may also have a connection to an onboard diagnostics connector (OBD-II), a CAN (Controller Area Network) bus, and/or other wired or wireless mechanisms. Via one or more such communications mechanisms, the computer 20 may transmit messages to various devices in a vehicle and/or receive messages from the various devices, e.g., controllers, actuators, sensors, etc., including data collectors 24 and controllers 26 . Alternatively or additionally, in cases where the computer 20 actually comprises multiple devices, the CAN bus or the like may be used for communications between devices represented as the computer 20 in this disclosure. In addition, the computer 20 may be configured for communicating with other devices via various wired and/or wireless networking technologies, e.g., cellular, Bluetooth, a universal serial bus (USB), wired and/or wireless packet networks, etc.
  • OBD-II onboard diagnostics connector
  • CAN Controller Area Network
  • the computer 20 may transmit messages to various devices in a vehicle and/or receive messages from the various devices, e.g., controllers, actuator
  • a memory of the computer 20 generally stores collected data. Collected data may include a variety of data collected in a host vehicle 14 by data collectors 24 and/or derived therefrom. Examples of collected data 24 may include, e.g., data about the driving history of one or more non-host vehicles 16 , e.g., the position (for example, geo-coordinates, a distance from the host vehicle 14 , etc.) of the non-host vehicle 16 as a function of time, the speed of the non-host vehicle 16 as a function of time, the direction of travel, the number and magnitude of changes in direction and speed at various time points, etc.
  • collected data 24 may include, e.g., data about the driving history of one or more non-host vehicles 16 , e.g., the position (for example, geo-coordinates, a distance from the host vehicle 14 , etc.) of the non-host vehicle 16 as a function of time, the speed of the non-host vehicle 16 as a function of time, the direction of travel, the number and magnitude
  • Collected data may further include, e.g., information such as a type (e.g., light truck, passenger car, minivan, etc.), dimensions, make, model, etc. of the one or more of the non-host vehicles 16 .
  • the collected data may additionally include data calculated from data received form data collectors 24 in the computer 20 .
  • the collected data may include any data that may be gathered by the data collectors 24 , received through vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) communications, collected or received from other sources, and/or computed from such data.
  • V2V vehicle-to-vehicle
  • V2I vehicle-to-infrastructure
  • the computer 20 may be programmed to receive data from the data collectors 24 and data related to the goals, e.g., destination, route, time of arrival, etc. of the host vehicle 14 . Based on the collected data, as described below, the computer 20 may define a traffic environment 10 , identify non-host vehicles 16 participating in the traffic environment 10 , and determine a policy 46 for the host vehicle 14 .
  • the computer 20 may further be programmed to collect data regarding the goals of the host vehicle 14 and other data related to the host vehicle 14 , e.g., maps of an area where the vehicle 14 is operating. For example, the computer 20 may receive input from the user via the user interface 22 indicating the destination of the user, the route the user would like to take, the driving style (conservative, sporty), etc.
  • the computer 20 may further include or receive, e.g., maps of the area, e.g., from a GPS system or from memory. Based on the received data, the computer 20 may perform what is referred to as “mission planning,” i.e., planning a path to a desired destination in terms of driving directions on a road network map.
  • the computer 20 may further be programmed to store this data in a memory for further use, e.g., for use in determining a driving policy 46 and/or in driving the host vehicle 14 .
  • the computer 20 may determine and send commands to vehicle controllers 26 to control the vehicle 14 according to the policy 46 and planned mission.
  • each controller 26 may include a processor programmed to receive instructions from the computer 20 , execute the instructions, and send messages to the computer 20 .
  • each of the controllers 26 may include or be communicatively coupled to an actuator or the like that is provided to actuate a vehicle component, e.g., brakes, steering, throttle, etc.
  • a brake controller 26 may include a processor and a pump for adjusting a pressure of brake fluid. In this example, upon receiving an instruction from the computer 20 , the processor may activate the pump in order to provide power assist or initiate a braking operation.
  • controllers 26 may each include sensors or otherwise operate as data collectors 24 to provide data to the computer 20 regarding vehicle speed, vehicle steering angle, height of a suspension, etc.
  • the brake control unit 26 may send data to the computer 20 corresponding to the brake pressure being applied by the brake controller 26 .
  • Data collectors 24 may include a variety of devices.
  • data collectors 24 may include lidar, radar, video cameras, ultrasonic sensors, infrared sensors for sensing the environment, and for example, tracking non-host vehicles 16 .
  • Data collectors 24 may further include components that collect dynamic host vehicle 14 data, such as velocity, yaw rate, steering angle, etc. Further, the foregoing examples are not intended to be limiting.
  • Other types of data collectors 24 for example accelerometers, gyroscopes, pressure sensors, thermometers, barometers, altimeters, etc., could be used to provide data to the computer 20 .
  • a road network definition file (RNDF) 25 may include encoded topological-metric maps of the road networks where the host vehicle 14 may be operating.
  • the topological-metric maps include latitude and longitude coordinates for road features and other objects in the environment and are encoded based on a derivative of the RNFD file format.
  • the RNDF 25 may supply map data, e.g., to the computer 20 .
  • the host vehicle 14 may further include a user interface 22 that may be included in or communicatively coupled to the computer 20 .
  • the user interface 22 can be used to allow a user to monitor a policy 46 selection procedure and/or to manually select policies 46 to execute.
  • the interface 22 may include one or more output devices such as a display, speakers, etc. for communicating information to a user.
  • the interface 22 may further include one or more input devices such as a touch screen display, a keyboard, a gesture recognition device, switches, etc., for receiving input from the user.
  • the computer 20 may be programmed to store data related to the non-host vehicles 16 .
  • this data may include data representing a history of data points, e.g., the pose of the non-host vehicle 16 as a function of time, a speed of the non-host vehicle 16 as a function of time, a direction of travel, a number and magnitude of changes in direction and speed at various time points, etc.
  • the history may be sampled periodically, e.g., every 0.3 s, with a maximum allowed number of history points.
  • the maximum allowed number of history points may be, e.g., 400 , which may show the previous two minutes of driving behavior for each non-host vehicle 16 .
  • the maximum allowed number of history points may depend on the type of driving situation currently being considered. For example, fewer history points may be necessary for a parking maneuver than for driving on a highway.
  • Collected data related to the non-host vehicles may further include, e.g., information about each of the non-host vehicles 16 such as the type, dimensions, make, model, etc.
  • the collected data may additionally include data calculated therefrom in the computer 20 .
  • the computer 20 memory further generally stores policies 46 .
  • Each policy 46 is designed to capture a different high-level behavior and intention, and may include a planned trajectory.
  • Example policies may include following a lane, changing a lane, or turning at an intersection.
  • the policies 46 may indicate one or more actions that a vehicle 14 , 16 may take in support of the policy. For example, for a lane-nominal policy (see below), the vehicle 14 , 16 may take actions to steer the vehicle toward a centerline of a current lane where the vehicle 14 is travelling.
  • the policies 46 may further indicate one or more reactions that a vehicle 14 , 16 may have to another vehicle 14 , 16 . For example, the vehicle 14 , 16 may adjust a speed of the vehicle 14 , 16 to maintain desired distances between other vehicles 14 , 16 in front of and/or behind the vehicle 14 , 16 in the same lane.
  • a non-limiting list of policies 46 includes:
  • the computer 20 may be programmed to identify a traffic environment 10 including a host vehicle 14 and one or more non-host vehicles 16 within a predefined distance to the host vehicle 14 .
  • a predefined distance may be defined, e.g., as within a first fixed distance on a left and right side, e.g., 20 meters, and a second fixed distance on a front and rear side, e.g., 100 meters.
  • the predefined distance may be defined as a function of a driving situation. For example, within a predefined distance may be defined as within a relatively small area if the host vehicle 14 is parking, and within a relatively large area if the host vehicle 14 is travelling on a highway. Further, the predefined distance may be defined, e.g., based on a speed that the host vehicle 14 is travelling, the policy 46 the vehicle 14 is currently executing, etc.
  • the computer 20 may be programmed to collect data regarding the driving behavior of the non-host vehicles 16 during a preceding time period.
  • the preceding time period may be, e.g., a predetermined period of time, for example two minutes, prior to a current time.
  • the data collected for each of the non-host vehicles 16 may include, e.g., the pose as a function of time, speed as a function of time, etc., as described above.
  • the data may also include information about the non-host vehicle 16 such as the type, model, size, etc. Still further, the data may include information such as the number, identity etc. of the occupants of the non-host vehicle 16 .
  • the computer 20 may be programmed, based on the collected data, to analyze the driving behavior of the one or more non-host vehicles 16 during the preceding time period. As shown in FIG. 3 , a non-host vehicle 16 may travel along a path 50 on a highway 12 including first, second and third lanes 60 a , 60 b , 60 c . The computer 20 may identify one or more segments 52 along the path 50 . Change-points 54 may be identified by the computer 20 that mark a transition from one segment 52 to another segment 52 .
  • Each segment 52 may be associated with a policy 46 which is a good fit to the observed behavior during the segment 52 .
  • a first segment 52 a , third segment 52 c and fifth segment 52 e may be associated with the policy 46 lane_nominal.
  • a second segment 52 b may be associated with the policy 46 lane_change_right and a fourth segment 52 d may be associated with the policy 46 lane_change_left.
  • Change-points 54 may be identified, marking a time (and position along the path 50 ) where a change in the underlying policy 46 governing the non-host vehicle 16 behavior is likely to have occurred.
  • the computer 20 may be programmed to compute the likelihood of all available policies 46 for the target vehicle given the observations in the most recent segment, capturing the distribution p( ⁇ t v
  • a known algorithm referred to as change-point detection using approximate parameters (CHAMP), discussed below, may be used to segment a history of observed states of a target non-host vehicle 16 .
  • CHAP change-point detection using approximate parameters
  • CHAMP infers the maximum a posteriori (MAP) set of times ⁇ 1 , ⁇ 2 , . . . , ⁇ m , at which changepoints 54 between policies have occurred, yielding m +1 segments 52 .
  • MAP maximum a posteriori
  • CHAMP Given a segment 52 from time s to t and a policy 46 ⁇ , CHAMP approximates the logarithm of the policy evidence for that segment 52 via a Bayesian information criterion (BIC) as: log L ( s,t , ⁇ ) ⁇ log p ( z s+1:t
  • BIC Bayesian information criterion
  • the BIC is a known approximation that avoids marginalizing over the policy parameters and provides a principled penalty against complex policies 46 by assuming a Gaussian posterior around the estimated parameters ⁇ circumflex over ( ⁇ ) ⁇ .
  • MLE maximum likelihood estimation
  • P t ⁇ ( j , q ) ( 1 - G ⁇ ( t - j - 1 ) ) ⁇ L ⁇ ( j , t , q ) ⁇ p ⁇ ( q ) ⁇ P j MAP ( 12 )
  • P t MAP max j , q ⁇ [ g ⁇ ( t - j ) 1 - G ⁇ ( t - j - 1 ) ⁇ P t ⁇ ( j , q ) ] , ( 13 )
  • the most likely sequence of latent policies 46 (called the Viterbi path) that results in the sequence of observations can be recovered by finding (j,q) that maximize P t MAP , and then repeating the maximization for P j MAP , successively until time zero is reached.
  • the computer 20 may further be programmed to compute the likelihood of each latent policy 46 by leveraging change-point detection on the history of observed vehicle states.
  • each latent policy 46 ⁇ for the non-host vehicle 16 given the present segment 52 can be computed by solving the following maximum likelihood estimation (MLE) problem:
  • Eq. 15 essentially measures the deviation of the observed states from those prescribed by the given policy 46 .
  • the policy likelihoods obtained via Eq. 14 capture the probability distribution over the possible policies 46 that the observed non-host vehicle 16 might be executing at the current timestep, which can be represented, using delta functions, as a mixture distribution:
  • Anomalous behavior of a non-host vehicle 16 not modeled by available policies 46 may be detected based on the time-series segmentation obtained via change-point detection.
  • the properties of anomalous behavior may be defined in terms of policy likelihoods.
  • the observed data may then be compared against labeled normal patterns in previously-recorded vehicle trajectories. The following two criteria may be defined for anomalous behavior:
  • ⁇ i is the policy 46 associated with the i th segment 52 .
  • This normality measure on the target vehicle's history can then be compared to that of a set of previously recorded trajectories of other non-host vehicles 16 .
  • a process may be developed and implemented for selecting a policy 46 to govern the behavior of the host vehicle 14 at the current timestep.
  • the process begins by drawing a set of samples s ⁇ S from the distribution over policies 46 of the non-host vehicles 16 via Eq. 16, where each sample assigns a policy 46 ⁇ v ⁇ to each nearby non-host vehicle 16 v .
  • each policy 46 ⁇ available to the host vehicle 14 and for each sample s, the computer 20 rolls out forward in time until a decision horizon H the host and non-host vehicles 14 , 16 under the policy assignments ( ⁇ ,s) with closed-loop simulation to yield a set ⁇ of simulated trajectories ⁇ .
  • a reward r ⁇ ,s for is evaluated for each rollout ⁇ , and finally a policy 46 ⁇ * is selected to maximize the expected reward.
  • the process continuously repeats in a receding horizon manner.
  • policies 46 that are not applicable given the current state x 0 such as an intersection handling policy 46 when driving on the highway, are not considered for selection.
  • An exemplary process for selecting a policy 46 to govern the host vehicle 14 is presented in more detail in the section “Exemplary Process Flow”, below.
  • each policy 46 is designed to capture a different high-level behavior and intention, and may include a planned trajectory.
  • Policies 46 may include, e.g., following a lane, changing a lane, or turning at an intersection.
  • Policies 46 available for a particular host vehicle 14 and/or non-host vehicle 16 may depend on the setting for the traffic environment 10 , i.e., on a highway, at an intersection, in a parking lot, etc.
  • a lower-fidelity simulation can capture the necessary interactions between vehicles 14 , 16 to make reasonable choices for host vehicle 14 behavior while providing faster performance.
  • a simplified simulation model for each vehicle 14 , 16 is used that assumes an idealized steering controller. Nonetheless, this simplification still faithfully describes the high-level behavior of the between-vehicle 14 , 16 interactions.
  • Vehicles 14 , 16 classified as anomalous may be simulated using a single policy 46 accounting only for their current state and map of the environment, because they are not likely to be modeled by the set of behaviors in our system.
  • the reward function for evaluating the outcome of a rollout ⁇ involving all non-host and host vehicles 14 , 16 is a weighted combination of metrics m q ( ⁇ ) ⁇ M, with weights w q that express user importance.
  • Typical metrics include the (remaining) distance to the goal at the end of the evaluation horizon to evaluate progress made toward the destination, minimum distance to obstacles to evaluate safety, a lane choice bias to add a preference for the right lane, and the maximum yaw rate and longitudinal jerk to measure passenger comfort.
  • the expected reward is used to target better average-case performance, as it is easy to become overly conservative when negotiating traffic if one only accounts for worst-case behavior. By weighting by the probability of each sample, we can avoid overcorrecting for low-probability events.
  • a non-limiting list of metrics which may considered for a sample rollout (forward simulation) includes:
  • the metric outcomes may be converted to normalized, unit-less values, weights may be determined for each metric, and a weighted sum of metrics may be computed for each sampled outcome.
  • the metric scores themselves have widely varying units between them, so to make them comparable, they may be normalized using a range of metric outcomes (e.g., with three policies 46 that get the host vehicle 14 respectively 10, 20 and 30 meters closer to the goal, respectively, the results may be normalized over the range, which is 20 meters, to values ranging from 0 to 1, yielding normalized metric scores of 0.0, 0.5 and 1.0, respectively).
  • weights may be computed that get set to zero when the range across a single metric is too low to be informative.
  • the final weights for each metric are either zero for uninformative metrics or a pre-determined weight chosen by the designer.
  • the final reward for each sampled rollout is a weighted sum of all the metrics.
  • a weighted sum of the rewards may be computed for each sample involved with a particular policy choice, with weights given by the probability of each sample.
  • the policy 46 may then be selected with the highest expected reward.
  • FIG. 4 is a diagram of an exemplary process 400 for controlling a vehicle using multipolicy decision-making.
  • the process 400 starts in a block 405 .
  • a host vehicle 14 computer 20 receives data representing a current environment in which the host vehicle 14 is currently operating.
  • the computer 20 may receive (or retrieve) map data describing the current road network where the host vehicle 14 is operating.
  • the computer 20 may further receive data regarding one or more non-host vehicles 16 travelling within a predefined distance to the host vehicle 14 .
  • the data may include the current position of each non-host vehicle 16 , and other data such as speed, direction of travel etc. as described above.
  • the computer 20 may receive data of other objects within the predefined distance to the host vehicle 14 , traffic signals, weather conditions, etc.
  • the process 400 continues in a block 410 .
  • the computer 20 identifies a traffic environment 10 including the host vehicle 14 and one or more non-host vehicles 16 within the predefined distance to the host vehicle 14 as described above.
  • the traffic environment 10 may be defined to include other elements in the environment, i.e., a road map, objects, etc. that may impact selection of a policy for driving the host vehicle 14 .
  • the process 400 continues in a block 415 .
  • the computer 20 collects behavioral data representing behaviors of each of the non-host vehicles 16 in the recent past.
  • the behavior data may include the pose of the non-host vehicle 16 as a function of time, a speed of the non-host vehicle 16 as a function of time, a direction of travel, a number and magnitude of changes in direction and speed at various time points, etc.
  • the history of driving behaviors may be sampled e.g., every 0.3 s, with a maximum allowed number of history points.
  • the maximum allowed number of history points may be, e.g., 400 , which may show the previous two minutes of driving behavior for each non-host vehicle 16 .
  • the maximum allowed number of history points may depend on the type of driving situation currently be considered. For example, fewer history points may be necessary for a parking maneuver than for driving on a highway.
  • the computer 20 analyzes the past behavior of the non-host vehicles 16 using Bayesian change-point analysis. Based on the change-point analysis, the computer 20 identifies a distribution of likely policies 46 for each of the non-host vehicles 16 at the current timestep. Then, the computer 20 identifies one or more policies 46 that may be used to govern the host vehicle 14 . The process 400 continues in a block 425 .
  • the computer 20 performs one or more forward simulations of the traffic environment 10 .
  • the computer 20 selects high likelihood samples from the distribution of likely policies 46 for each of the non-host vehicles 16 and also from the one or more policies 46 for the host vehicle 14 . Multiple simulations are run based on different sets of selected policies 46 for the non-host vehicles 16 and host vehicles 14 .
  • the process 400 then continues in a block 430 .
  • the computer 20 evaluates the results of the multiple simulations based on a set of rewards established for the traffic environment 10 .
  • the computer 20 selects a policy 46 to govern the host vehicle 46 in order to maximize the rewards for the traffic environment 10 as described above.
  • the process 400 continues in a block 435 .
  • the computer 20 sends the selected policy 46 to the vehicle control unit 34 .
  • the vehicle control unit 34 based at least in part on the policy 46 , issues commands to one or more controllers 26 to control the driving behavior of the vehicle 14 .
  • the process continues in a block 440 .
  • the computer 20 determines if the process 400 should continue. For example, if the host vehicle 14 continues to move, the process 400 may return the block 405 and reevaluate the definition of the traffic environment 10 . If, on the other hand, the ignition of the host vehicle 14 is turned off, the vehicle 14 has stopped moving (is parked), or if there has been a traffic event such as a collision, the computer 20 may determine that the process 400 should end.
  • the adverb “substantially” means that a shape, structure, measurement, quantity, time, etc. may deviate from an exact described geometry, distance, measurement, quantity, time, etc., because of imperfections in materials, machining, manufacturing, etc.
  • exemplary is used herein in the sense of signifying an example, e.g., a reference to an “exemplary widget” should be read as simply referring to an example of a widget.
  • Computing devices such as those discussed herein generally each include instructions executable by one or more computing devices such as those identified above, and for carrying out blocks or steps of processes described above.
  • process blocks discussed above may be embodied as computer-executable instructions.
  • Computer-executable instructions may be compiled or interpreted from computer programs created using a variety of programming languages and/or technologies, including, without limitation, and either alone or in combination, JavaTM, C, C++, Visual Basic, Java Script, Perl, HTML, etc.
  • a processor e.g., a microprocessor
  • receives instructions e.g., from a memory, a computer-readable medium, etc., and executes these instructions, thereby performing one or more processes, including one or more of the processes described herein.
  • Such instructions and other data may be stored and transmitted using a variety of computer-readable media.
  • a file in a computing device is generally a collection of data stored on a computer readable medium, such as a storage medium, a random access memory, etc.
  • Computer-readable media include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, DVD, any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, a RAM, a PROM, an EPROM, a FLASH-EEPROM, any other memory chip or cartridge, or any other medium from which a computer can read.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
US14/814,766 2015-07-31 2015-07-31 Vehicle trajectory determination Active 2035-08-19 US9934688B2 (en)

Priority Applications (5)

Application Number Priority Date Filing Date Title
US14/814,766 US9934688B2 (en) 2015-07-31 2015-07-31 Vehicle trajectory determination
MX2016009489A MX365104B (es) 2015-07-31 2016-07-21 Determinacion de la trayectoria de vehiculos.
RU2016130094A RU2681984C1 (ru) 2015-07-31 2016-07-22 Система и способ определения траектории для транспортного средства
CN201610595858.6A CN106428009B (zh) 2015-07-31 2016-07-26 车辆轨迹确定的系统和方法
DE102016113903.3A DE102016113903A1 (de) 2015-07-31 2016-07-27 Fahrzeugfahrstreckenbestimmung

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US14/814,766 US9934688B2 (en) 2015-07-31 2015-07-31 Vehicle trajectory determination

Publications (2)

Publication Number Publication Date
US20170031361A1 US20170031361A1 (en) 2017-02-02
US9934688B2 true US9934688B2 (en) 2018-04-03

Family

ID=57882607

Family Applications (1)

Application Number Title Priority Date Filing Date
US14/814,766 Active 2035-08-19 US9934688B2 (en) 2015-07-31 2015-07-31 Vehicle trajectory determination

Country Status (5)

Country Link
US (1) US9934688B2 (es)
CN (1) CN106428009B (es)
DE (1) DE102016113903A1 (es)
MX (1) MX365104B (es)
RU (1) RU2681984C1 (es)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11087621B2 (en) * 2017-11-06 2021-08-10 Huawei Technologies Co., Ltd. Express lane planning method and unit
US20220048513A1 (en) * 2020-08-12 2022-02-17 Honda Motor Co., Ltd. Probabilistic-based lane-change decision making and motion planning system and method thereof
US11275379B2 (en) 2017-06-02 2022-03-15 Honda Motor Co., Ltd. Vehicle control apparatus and method for controlling automated driving vehicle
US20220266852A1 (en) * 2021-02-19 2022-08-25 Aptiv Technologies Limited Vehicle Lateral-Control System with Dynamically Adjustable Calibrations
US11435748B2 (en) * 2017-10-28 2022-09-06 Tusimple, Inc. System and method for real world autonomous vehicle trajectory simulation
US20220332320A1 (en) * 2021-04-20 2022-10-20 Hyundai Mobis Co., Ltd. Vehicle control system and method
US11491987B1 (en) * 2022-06-22 2022-11-08 Embark Trucks Inc. Merge handling based on merge intentions over time
US11495028B2 (en) * 2018-09-28 2022-11-08 Intel Corporation Obstacle analyzer, vehicle control system, and methods thereof
US20230192074A1 (en) * 2021-12-20 2023-06-22 Waymo Llc Systems and Methods to Determine a Lane Change Strategy at a Merge Region
US11710303B2 (en) 2017-08-23 2023-07-25 Uatc, Llc Systems and methods for prioritizing object prediction for autonomous vehicles
US11853065B2 (en) 2018-12-20 2023-12-26 Volkswagen Aktiengesellschaft Method and driver assistance system for assisting a driver of a vehicle with driving of the vehicle

Families Citing this family (140)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10486707B2 (en) * 2016-01-06 2019-11-26 GM Global Technology Operations LLC Prediction of driver intent at intersection
US10449967B1 (en) 2016-03-01 2019-10-22 Allstate Insurance Company Vehicle to vehicle telematics
US10062288B2 (en) * 2016-07-29 2018-08-28 GM Global Technology Operations LLC Systems and methods for autonomous driving merging management
US10635117B2 (en) * 2016-10-25 2020-04-28 International Business Machines Corporation Traffic navigation for a lead vehicle and associated following vehicles
JP6592423B2 (ja) * 2016-11-25 2019-10-16 株式会社デンソー 車両制御装置
US10852730B2 (en) * 2017-02-08 2020-12-01 Brain Corporation Systems and methods for robotic mobile platforms
US10654476B2 (en) 2017-02-10 2020-05-19 Nissan North America, Inc. Autonomous vehicle operational management control
JP6890757B2 (ja) * 2017-02-10 2021-06-18 ニッサン ノース アメリカ，インク 部分観測マルコフ決定過程モデルインスタンスを動作させることを含む自律走行車動作管理
WO2018147871A1 (en) * 2017-02-10 2018-08-16 Nissan North America, Inc. Autonomous vehicle operational management
EP3580104B1 (en) 2017-02-10 2020-11-11 Nissan North America, Inc. Autonomous vehicle operational management blocking monitoring
US10353390B2 (en) 2017-03-01 2019-07-16 Zoox, Inc. Trajectory generation and execution architecture
US10671076B1 (en) * 2017-03-01 2020-06-02 Zoox, Inc. Trajectory prediction of third-party objects using temporal logic and tree search
KR102309420B1 (ko) * 2017-03-03 2021-10-07 현대자동차주식회사 차량 및 그 제어방법
US11087200B2 (en) 2017-03-17 2021-08-10 The Regents Of The University Of Michigan Method and apparatus for constructing informative outcomes to guide multi-policy decision making
WO2018172849A1 (en) * 2017-03-20 2018-09-27 Mobileye Vision Technologies Ltd. Trajectory selection for an autonomous vehicle
US10994729B2 (en) * 2017-03-29 2021-05-04 Mitsubishi Electric Research Laboratories, Inc. System and method for controlling lateral motion of vehicle
DE102017206862A1 (de) * 2017-04-24 2018-10-25 Bayerische Motoren Werke Aktiengesellschaft Auswählen einer Handlungsoption betreffend die Längsführung eines Kraftfahrzeugs mit zumindest automatisierter Längsführung
DE102017207463A1 (de) * 2017-05-04 2018-11-08 Bayerische Motoren Werke Aktiengesellschaft Vorrichtung zum Aktivieren/Deaktivieren eines Sicherheitssystems eines Kraftfahrzeugs bei einem Abbiegevorgang des Kraftfahrzeugs
EP3401182B1 (en) 2017-05-09 2020-09-09 Veoneer Sweden AB Apparatus for lane detection
DE102017208168A1 (de) * 2017-05-15 2018-11-15 Continental Automotive Gmbh Verfahren zum Erzeugen einer Überholwahrscheinlichkeitssammlung, Verfahren zum Betreiben einer Steuereinrichtung eines Kraftfahrzeugs, Überholwahrscheinlichkeitssammeleinrichtung und Steuereinrichtung
CN107298100B (zh) * 2017-05-16 2019-05-10 开易（北京）科技有限公司 一种基于高斯混合模型的车辆轨迹预测方法、系统
DE112017007600T5 (de) * 2017-06-02 2020-02-20 Honda Motor Co., Ltd. Fahrzeug-Steuervorrichtung und Verfahren zum Steuern eines automatisiert fahrenden Fahrzeugs
US11364899B2 (en) * 2017-06-02 2022-06-21 Toyota Motor Europe Driving assistance method and system
CN110809542B (zh) * 2017-06-30 2021-05-11 华为技术有限公司 车辆的控制方法、装置及设备
US10296785B1 (en) * 2017-07-24 2019-05-21 State Farm Mutual Automobile Insurance Company Apparatuses, systems, and methods for vehicle operator gesture recognition and transmission of related gesture data
FR3070658B1 (fr) * 2017-09-06 2019-08-30 IFP Energies Nouvelles Procede de determination d'une vitesse a atteindre pour un premier vehicule precede par un deuxieme vehicule, en particulier pour un vehicule autonome
US20190079517A1 (en) 2017-09-08 2019-03-14 nuTonomy Inc. Planning autonomous motion
KR101989102B1 (ko) * 2017-09-13 2019-06-13 엘지전자 주식회사 차량용 운전 보조 장치 및 그 제어 방법
US10739776B2 (en) * 2017-10-12 2020-08-11 Honda Motor Co., Ltd. Autonomous vehicle policy generation
US11093829B2 (en) * 2017-10-12 2021-08-17 Honda Motor Co., Ltd. Interaction-aware decision making
US11657266B2 (en) 2018-11-16 2023-05-23 Honda Motor Co., Ltd. Cooperative multi-goal, multi-agent, multi-stage reinforcement learning
CN107909837A (zh) * 2017-10-24 2018-04-13 华为技术有限公司 一种车辆借道通行的方法和控制中心
US10836405B2 (en) 2017-10-30 2020-11-17 Nissan North America, Inc. Continual planning and metareasoning for controlling an autonomous vehicle
WO2019088989A1 (en) 2017-10-31 2019-05-09 Nissan North America, Inc. Reinforcement and model learning for vehicle operation
US11702070B2 (en) 2017-10-31 2023-07-18 Nissan North America, Inc. Autonomous vehicle operation with explicit occlusion reasoning
US20180079422A1 (en) * 2017-11-27 2018-03-22 GM Global Technology Operations LLC Active traffic participant
WO2019108213A1 (en) * 2017-11-30 2019-06-06 Nissan North America, Inc. Autonomous vehicle operational management scenarios
DE102017221634B4 (de) * 2017-12-01 2019-09-05 Audi Ag Kraftfahrzeug mit einem Fahrzeugführungssystem, Verfahren zum Betrieb eines Fahrzeugführungssystems und Computerprogramm
US11360475B2 (en) * 2017-12-05 2022-06-14 Waymo Llc Real-time lane change selection for autonomous vehicles
US11260875B2 (en) * 2017-12-07 2022-03-01 Uatc, Llc Systems and methods for road surface dependent motion planning
DE102017222871A1 (de) * 2017-12-15 2019-06-19 Zf Friedrichshafen Ag Signalisieren einer Fahrentscheidung eines automatisiert betreibbaren Fahrzeuges für einen Verkehrsteilnehmer
US11130497B2 (en) 2017-12-18 2021-09-28 Plusai Limited Method and system for ensemble vehicle control prediction in autonomous driving vehicles
US11273836B2 (en) 2017-12-18 2022-03-15 Plusai, Inc. Method and system for human-like driving lane planning in autonomous driving vehicles
US20190185012A1 (en) 2017-12-18 2019-06-20 PlusAI Corp Method and system for personalized motion planning in autonomous driving vehicles
CN109935106A (zh) * 2017-12-18 2019-06-25 成都配天智能技术有限公司 一种车辆信息交互方法、装置、车辆及存储介质
US11874120B2 (en) 2017-12-22 2024-01-16 Nissan North America, Inc. Shared autonomous vehicle operational management
CN111527013B (zh) * 2017-12-27 2024-02-23 宝马股份公司 车辆变道预测
JP7007183B2 (ja) * 2017-12-27 2022-01-24 日立Astemo株式会社 交通流制御装置、走行シナリオのデータ構造
US20190204842A1 (en) * 2018-01-02 2019-07-04 GM Global Technology Operations LLC Trajectory planner with dynamic cost learning for autonomous driving
CN108297866B (zh) * 2018-01-03 2019-10-15 西安交通大学 一种车辆的车道保持控制方法
WO2019138498A1 (ja) * 2018-01-11 2019-07-18 住友電気工業株式会社 車載装置、調整方法、およびコンピュータプログラム
US10745006B2 (en) * 2018-02-01 2020-08-18 GM Global Technology Operations LLC Managing automated driving complexity of the forward path using perception system measures
WO2019152888A1 (en) 2018-02-02 2019-08-08 Nvidia Corporation Safety procedure analysis for obstacle avoidance in autonomous vehicle
US10955851B2 (en) 2018-02-14 2021-03-23 Zoox, Inc. Detecting blocking objects
CN111902782A (zh) 2018-02-26 2020-11-06 北美日产公司 集中式共享自主运载工具操作管理
US10782699B2 (en) * 2018-03-10 2020-09-22 Baidu Usa Llc Real-time perception adjustment and driving adaption based on surrounding vehicles' behavior for autonomous driving vehicles
US11077845B2 (en) * 2018-03-20 2021-08-03 Mobileye Vision Technologies Ltd. Systems and methods for navigating a vehicle
US10414395B1 (en) 2018-04-06 2019-09-17 Zoox, Inc. Feature-based prediction
CN108710637B (zh) * 2018-04-11 2021-06-04 上海交通大学 基于时空关系的出租车异常轨迹实时检测方法
DE102018207102A1 (de) * 2018-05-08 2019-11-14 Robert Bosch Gmbh Verfahren zur Ermittlung der Trajektorienfolgegenauigkeit
US10860025B2 (en) * 2018-05-15 2020-12-08 Toyota Research Institute, Inc. Modeling graph of interactions between agents
US11126873B2 (en) 2018-05-17 2021-09-21 Zoox, Inc. Vehicle lighting state determination
CN108860167A (zh) * 2018-06-04 2018-11-23 立旃（上海）科技有限公司 基于区块链的自动驾驶控制方法及装置
US10860023B2 (en) * 2018-06-25 2020-12-08 Mitsubishi Electric Research Laboratories, Inc. Systems and methods for safe decision making of autonomous vehicles
US11120688B2 (en) 2018-06-29 2021-09-14 Nissan North America, Inc. Orientation-adjust actions for autonomous vehicle operational management
CN109060370B (zh) * 2018-06-29 2019-12-10 奇瑞汽车股份有限公司 对自动驾驶车辆进行车辆测试的方法及装置
EP3598413A1 (en) * 2018-07-19 2020-01-22 Volkswagen Aktiengesellschaft Apparatus, method, and computer program for a mobile transceiver
WO2020018688A1 (en) 2018-07-20 2020-01-23 May Mobility, Inc. A multi-perspective system and method for behavioral policy selection by an autonomous agent
DE102018217775A1 (de) 2018-09-13 2019-01-17 Robert Bosch Gmbh Verfahren zum Vorbereiten und Durchführen einer Manöverplanung wenigstens eines Fahrzeugs
US11195418B1 (en) * 2018-10-04 2021-12-07 Zoox, Inc. Trajectory prediction on top-down scenes and associated model
US11169531B2 (en) 2018-10-04 2021-11-09 Zoox, Inc. Trajectory prediction on top-down scenes
TWI695280B (zh) * 2018-10-08 2020-06-01 財團法人資訊工業策進會 為一生產線之一預設控制條件組決定一目標調整路徑之裝置及方法
EP3864574A1 (en) * 2018-10-16 2021-08-18 Five AI Limited Autonomous vehicle planning and prediction
US10940863B2 (en) * 2018-11-01 2021-03-09 GM Global Technology Operations LLC Spatial and temporal attention-based deep reinforcement learning of hierarchical lane-change policies for controlling an autonomous vehicle
EP3650297B1 (en) * 2018-11-08 2023-06-14 Bayerische Motoren Werke Aktiengesellschaft Method and apparatus for determining information related to a lane change of a target vehicle, and computer program
TWI674984B (zh) * 2018-11-15 2019-10-21 財團法人車輛研究測試中心 自動駕駛車輛之行駛軌跡規劃系統及方法
EP3653459B1 (en) * 2018-11-15 2021-07-14 Volvo Car Corporation Vehicle safe stop
DE102018220775A1 (de) 2018-12-03 2020-06-04 Robert Bosch Gmbh Leitvorrichtung für wenigstens ein Fahrzeug
DE102018221178A1 (de) 2018-12-06 2020-06-10 Robert Bosch Gmbh Lokalisierungssystem
KR102673297B1 (ko) * 2018-12-07 2024-06-10 현대자동차주식회사 차량 주행 제어 장치, 그를 포함한 시스템 및 그 방법
DE102018221864A1 (de) * 2018-12-17 2020-06-18 Volkswagen Aktiengesellschaft Verfahren und System zum Bestimmen einer Trajektorie eines Fahrzeugs
US20200202706A1 (en) * 2018-12-20 2020-06-25 Qualcomm Incorporated Message Broadcasting for Vehicles
US10969470B2 (en) 2019-02-15 2021-04-06 May Mobility, Inc. Systems and methods for intelligently calibrating infrastructure devices using onboard sensors of an autonomous agent
CN109739246B (zh) 2019-02-19 2022-10-11 阿波罗智能技术(北京)有限公司 一种变换车道过程中的决策方法、装置、设备及存储介质
US11580445B2 (en) * 2019-03-05 2023-02-14 Salesforce.Com, Inc. Efficient off-policy credit assignment
US10962371B2 (en) * 2019-04-02 2021-03-30 GM Global Technology Operations LLC Method and apparatus of parallel tracking and localization via multi-mode slam fusion process
JP7251294B2 (ja) * 2019-04-25 2023-04-04 株式会社アドヴィックス 車両の走行制御装置
KR20200129045A (ko) 2019-05-07 2020-11-17 모셔널 에이디 엘엘씨 차량의 궤적을 계획 및 업데이트하기 위한 시스템 및 방법
DE102019112625A1 (de) * 2019-05-14 2020-11-19 Eyyes Gmbh Verfahren zum Anzeigen und/oder Berechnen einer Relativbewegung
US11242054B2 (en) * 2019-06-12 2022-02-08 Honda Motor Co., Ltd. Autonomous vehicle interactive decision making
CN112078592B (zh) * 2019-06-13 2021-12-24 魔门塔(苏州)科技有限公司 一种车辆行为和/或车辆轨迹的预测方法及装置
US20200406894A1 (en) * 2019-06-28 2020-12-31 Zoox, Inc. System and method for determining a target vehicle speed
CN112208531B (zh) * 2019-07-09 2024-04-30 本田技研工业株式会社 车辆控制装置、车辆控制方法及存储介质
DE102019004842A1 (de) * 2019-07-12 2021-01-14 Zf Friedrichshafen Ag Verfahren zum Betreiben eines wenigstens teilweise automatisierten Fahrzeugs
CN112242069B (zh) * 2019-07-17 2021-10-01 华为技术有限公司 一种确定车速的方法和装置
US20210039664A1 (en) * 2019-08-08 2021-02-11 Toyota Jidosha Kabushiki Kaisha Machine learning system for modifying adas behavior to provide optimum vehicle trajectory in a region
CN110497906B (zh) * 2019-08-30 2021-11-02 北京百度网讯科技有限公司 车辆控制方法、装置、设备和介质
US11663514B1 (en) * 2019-08-30 2023-05-30 Apple Inc. Multimodal input processing system
US11340622B2 (en) * 2019-08-30 2022-05-24 Waymo Llc Determining respective impacts of agents
CN112634396B (zh) * 2019-09-24 2024-06-18 北京四维图新科技股份有限公司 路网确定方法及装置
DE102019215680B3 (de) * 2019-10-11 2021-01-07 Audi Ag Verfahren zum Vorhersagen eines Verhaltens eines Zielfahrzeugs
WO2021092334A1 (en) * 2019-11-06 2021-05-14 Ohio State Innovation Foundation Systems and methods for vehicle dynamics and powertrain control using multiple horizon optimization
JP2021077088A (ja) * 2019-11-08 2021-05-20 ソニー株式会社 情報処理装置、情報処理方法及び情報処理プログラム
US11635758B2 (en) 2019-11-26 2023-04-25 Nissan North America, Inc. Risk aware executor with action set recommendations
US11899454B2 (en) 2019-11-26 2024-02-13 Nissan North America, Inc. Objective-based reasoning in autonomous vehicle decision-making
CN112987773B (zh) * 2019-12-02 2024-04-26 阿里巴巴集团控股有限公司 一种飞行轨迹的处理方法、装置及电子设备
WO2021122857A1 (en) * 2019-12-16 2021-06-24 Kontrol Gmbh Safe path planning method for mechatronic systems
US11613269B2 (en) * 2019-12-23 2023-03-28 Nissan North America, Inc. Learning safety and human-centered constraints in autonomous vehicles
CN111123933B (zh) * 2019-12-24 2021-10-01 华为技术有限公司 车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车
US11300957B2 (en) 2019-12-26 2022-04-12 Nissan North America, Inc. Multiple objective explanation and control interface design
US11577746B2 (en) 2020-01-31 2023-02-14 Nissan North America, Inc. Explainability of autonomous vehicle decision making
US11714971B2 (en) 2020-01-31 2023-08-01 Nissan North America, Inc. Explainability of autonomous vehicle decision making
JP7313298B2 (ja) * 2020-02-13 2023-07-24 本田技研工業株式会社 車両制御装置、車両制御方法、およびプログラム
US11782438B2 (en) 2020-03-17 2023-10-10 Nissan North America, Inc. Apparatus and method for post-processing a decision-making model of an autonomous vehicle using multivariate data
US12077190B2 (en) 2020-05-18 2024-09-03 Nvidia Corporation Efficient safety aware path selection and planning for autonomous machine applications
CN111505965B (zh) * 2020-06-17 2020-09-29 深圳裹动智驾科技有限公司 自动驾驶车辆仿真测试的方法、装置、计算机设备及存储介质
JP2023533225A (ja) 2020-07-01 2023-08-02 メイ モビリティー，インコーポレイテッド 自律走行車ポリシーを動的にキュレーションする方法及びシステム
US11814075B2 (en) * 2020-08-26 2023-11-14 Motional Ad Llc Conditional motion predictions
CN112068445B (zh) * 2020-09-23 2021-05-25 北京理工大学 自动驾驶车辆路径规划与路径跟踪集成控制方法及系统
CN114379555A (zh) * 2020-10-22 2022-04-22 奥迪股份公司 车辆变道控制方法、装置、设备及存储介质
CN114440908B (zh) * 2020-10-31 2023-07-28 华为技术有限公司 一种规划车辆驾驶路径的方法、装置、智能车以及存储介质
US20220144256A1 (en) * 2020-11-10 2022-05-12 Nec Laboratories America, Inc. Divide-and-conquer for lane-aware diverse trajectory prediction
US11753041B2 (en) 2020-11-23 2023-09-12 Waymo Llc Predicting behaviors of road agents using intermediate intention signals
RU2770239C1 (ru) * 2020-11-30 2022-04-14 Общество с ограниченной ответственностью «Яндекс Беспилотные Технологии» Способ и система определения траектории транспортного средства через слепую зону
US11851081B2 (en) 2020-12-01 2023-12-26 Waymo Llc Predictability-based autonomous vehicle trajectory assessments
WO2022132774A1 (en) 2020-12-14 2022-06-23 May Mobility, Inc. Autonomous vehicle safety platform system and method
JP7567059B2 (ja) 2020-12-17 2024-10-15 メイ モビリティー，インコーポレイテッド 自律エージェントの環境表現を動的に更新するための方法およびシステム
EP4314708A1 (en) 2021-04-02 2024-02-07 May Mobility, Inc. Method and system for operating an autonomous agent with incomplete environmental information
KR20220148011A (ko) * 2021-04-28 2022-11-04 주식회사 에이치엘클레무브 차량의 주행을 보조하는 장치 및 그 방법
CN113156963B (zh) * 2021-04-29 2022-08-12 重庆大学 基于监督信号引导的深度强化学习自动驾驶汽车控制方法
CN113177508B (zh) * 2021-05-18 2022-04-08 中移(上海)信息通信科技有限公司 一种行车信息的处理方法、装置及设备
CN113212454B (zh) * 2021-05-20 2023-05-12 中国第一汽车股份有限公司 车辆行驶状态的调整方法、装置、计算机设备和存储介质
JP2024526037A (ja) 2021-06-02 2024-07-17 メイ モビリティー，インコーポレイテッド 自律エージェントの遠隔支援のための方法及びシステム
US12012123B2 (en) 2021-12-01 2024-06-18 May Mobility, Inc. Method and system for impact-based operation of an autonomous agent
DE102021214759A1 (de) 2021-12-21 2023-06-22 Robert Bosch Gesellschaft mit beschränkter Haftung Erstellen von Folgeabstands-Profilen
CN114291116B (zh) * 2022-01-24 2023-05-16 广州小鹏自动驾驶科技有限公司 周围车辆轨迹预测方法、装置、车辆及存储介质
CN114648882B (zh) * 2022-02-09 2023-05-09 上海欧菲智能车联科技有限公司 一种车位检测方法及装置
WO2023154568A1 (en) 2022-02-14 2023-08-17 May Mobility, Inc. Method and system for conditional operation of an autonomous agent
CN114506344B (zh) * 2022-03-10 2024-03-08 福瑞泰克智能系统有限公司 一种车辆轨迹的确定方法及装置
WO2024129832A1 (en) 2022-12-13 2024-06-20 May Mobility, Inc. Method and system for assessing and mitigating risks encounterable by an autonomous vehicle

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100010699A1 (en) 2006-11-01 2010-01-14 Koji Taguchi Cruise control plan evaluation device and method
US20110246156A1 (en) 2008-12-23 2011-10-06 Continental Safety Engineering International Gmbh Method for Determining the Probability of a Collision of a Vehicle With a Living Being
US20120010762A1 (en) * 2009-03-23 2012-01-12 Honda Motor Co., Ltd. Information providing device for vehicle
US20120143488A1 (en) 2009-08-31 2012-06-07 Toyota Motor Europe Nv/Sa Vehicle or traffic control method and system
US20130099911A1 (en) * 2011-10-20 2013-04-25 GM Global Technology Operations LLC Highway Merge Assistant and Control
US8457827B1 (en) 2012-03-15 2013-06-04 Google Inc. Modifying behavior of autonomous vehicle based on predicted behavior of other vehicles
US20130158794A1 (en) 2009-06-16 2013-06-20 Tomtom North America Inc. Methods and systems for generating a horizon for use in an advanced driver assistance system (adas)
US8788134B1 (en) 2013-01-04 2014-07-22 GM Global Technology Operations LLC Autonomous driving merge management system
US8849557B1 (en) * 2012-11-15 2014-09-30 Google Inc. Leveraging of behavior of vehicles to detect likely presence of an emergency vehicle
US20140358841A1 (en) * 2012-01-20 2014-12-04 Toyota Jidosha Kabushiki Kaisha Vehicle behavior prediction device and vehicle behavior prediction method, and driving assistance device

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5407764B2 (ja) * 2009-10-30 2014-02-05 トヨタ自動車株式会社 運転支援装置
WO2013031095A1 (ja) * 2011-08-31 2013-03-07 日産自動車株式会社 車両運転支援装置
RU2479015C1 (ru) * 2012-01-11 2013-04-10 Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Санкт-Петербургский государственный электротехнический университет "ЛЭТИ" им. В.И. Ульянова (Ленина)" Способ определения траектории движения автономного транспортного средства в динамической среде

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100010699A1 (en) 2006-11-01 2010-01-14 Koji Taguchi Cruise control plan evaluation device and method
US20110246156A1 (en) 2008-12-23 2011-10-06 Continental Safety Engineering International Gmbh Method for Determining the Probability of a Collision of a Vehicle With a Living Being
US20120010762A1 (en) * 2009-03-23 2012-01-12 Honda Motor Co., Ltd. Information providing device for vehicle
US20130158794A1 (en) 2009-06-16 2013-06-20 Tomtom North America Inc. Methods and systems for generating a horizon for use in an advanced driver assistance system (adas)
US20120143488A1 (en) 2009-08-31 2012-06-07 Toyota Motor Europe Nv/Sa Vehicle or traffic control method and system
US20130099911A1 (en) * 2011-10-20 2013-04-25 GM Global Technology Operations LLC Highway Merge Assistant and Control
US20140358841A1 (en) * 2012-01-20 2014-12-04 Toyota Jidosha Kabushiki Kaisha Vehicle behavior prediction device and vehicle behavior prediction method, and driving assistance device
US8457827B1 (en) 2012-03-15 2013-06-04 Google Inc. Modifying behavior of autonomous vehicle based on predicted behavior of other vehicles
US20130261872A1 (en) * 2012-03-15 2013-10-03 Google Inc. Modifying Behavior of Autonomous Vehicle Based on Predicted Behavior of Other Vehicles
US8849557B1 (en) * 2012-11-15 2014-09-30 Google Inc. Leveraging of behavior of vehicles to detect likely presence of an emergency vehicle
US8788134B1 (en) 2013-01-04 2014-07-22 GM Global Technology Operations LLC Autonomous driving merge management system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Gindele, Tobias; Brechtel, Sebastian; Dillman, Rudiger; A Probabilistic Model for Estimating Driver Behaviors and Vehicle Trajectories in Traffic Environments, 2010 13th International IEEE Annual Conference on Intelligent Transportation Systems, Madeira Island, Portugal, Sep. 19-22, 2010; Institute for Anthropomatics, Karlsruhe Institute of Technology, Germany.
S Niekum, S. Osentoski, C. G. Atkeson, and A.G. Barto. CHAMP: Changepoint detection using approximate model parameters. Technical Report CMU-RI-TR-14-10, Robotics Institute, Carnegie Mellon University, 2014. *

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11275379B2 (en) 2017-06-02 2022-03-15 Honda Motor Co., Ltd. Vehicle control apparatus and method for controlling automated driving vehicle
US11710303B2 (en) 2017-08-23 2023-07-25 Uatc, Llc Systems and methods for prioritizing object prediction for autonomous vehicles
US20230004165A1 (en) * 2017-10-28 2023-01-05 Tusimple, Inc. System and method for real world autonomous vehicle trajectory simulation
US11435748B2 (en) * 2017-10-28 2022-09-06 Tusimple, Inc. System and method for real world autonomous vehicle trajectory simulation
US20240103523A1 (en) * 2017-10-28 2024-03-28 Tusimple, Inc. System and method for real world autonomous vehicle trajectory simulation
US11853072B2 (en) * 2017-10-28 2023-12-26 Tusimple, Inc. System and method for real world autonomous vehicle trajectory simulation
US11087621B2 (en) * 2017-11-06 2021-08-10 Huawei Technologies Co., Ltd. Express lane planning method and unit
US11495028B2 (en) * 2018-09-28 2022-11-08 Intel Corporation Obstacle analyzer, vehicle control system, and methods thereof
US11853065B2 (en) 2018-12-20 2023-12-26 Volkswagen Aktiengesellschaft Method and driver assistance system for assisting a driver of a vehicle with driving of the vehicle
US11608067B2 (en) * 2020-08-12 2023-03-21 Honda Motor Co., Ltd. Probabilistic-based lane-change decision making and motion planning system and method thereof
US20220048513A1 (en) * 2020-08-12 2022-02-17 Honda Motor Co., Ltd. Probabilistic-based lane-change decision making and motion planning system and method thereof
US11731648B2 (en) * 2021-02-19 2023-08-22 Aptiv Technologies Limited Vehicle lateral—control system with dynamically adjustable calibrations
US20220266852A1 (en) * 2021-02-19 2022-08-25 Aptiv Technologies Limited Vehicle Lateral-Control System with Dynamically Adjustable Calibrations
US20220332320A1 (en) * 2021-04-20 2022-10-20 Hyundai Mobis Co., Ltd. Vehicle control system and method
US20230192074A1 (en) * 2021-12-20 2023-06-22 Waymo Llc Systems and Methods to Determine a Lane Change Strategy at a Merge Region
US11987237B2 (en) * 2021-12-20 2024-05-21 Waymo Llc Systems and methods to determine a lane change strategy at a merge region
US11840234B1 (en) * 2022-06-22 2023-12-12 Embark Trucks Inc. Merge handling based on merge intentions over time
US11491987B1 (en) * 2022-06-22 2022-11-08 Embark Trucks Inc. Merge handling based on merge intentions over time
US20230415743A1 (en) * 2022-06-22 2023-12-28 Embark Trucks Inc. Merge handling based on merge intentions over time

Also Published As

Publication number Publication date
CN106428009A (zh) 2017-02-22
RU2681984C1 (ru) 2019-03-14
DE102016113903A1 (de) 2017-03-02
CN106428009B (zh) 2021-09-07
RU2016130094A (ru) 2018-01-23
MX365104B (es) 2019-05-22
MX2016009489A (es) 2017-07-19
US20170031361A1 (en) 2017-02-02

Similar Documents

Publication Publication Date Title
US9934688B2 (en) Vehicle trajectory determination
CN112840350B (zh) 自动驾驶车辆规划和预测
US9784592B2 (en) Turn predictions
US11835962B2 (en) Analysis of scenarios for controlling vehicle operations
US10324469B2 (en) System and method for controlling motion of vehicle in shared environment
AU2019253703B2 (en) Improving the safety of reinforcement learning models
CN112334368B (zh) 车辆控制系统及控制车辆运动的控制方法
CN110461676B (zh) 控制车辆的横向运动的系统和方法
Galceran et al. Multipolicy Decision-Making for Autonomous Driving via Changepoint-based Behavior Prediction.
US10831208B2 (en) Vehicle neural network processing
US11794731B2 (en) Waypoint prediction for vehicle motion planning
US11351996B2 (en) Trajectory prediction of surrounding vehicles using predefined routes
Chae et al. Virtual target-based overtaking decision, motion planning, and control of autonomous vehicles
CN116249947A (zh) 预测运动规划系统及方法
US20220227397A1 (en) Dynamic model evaluation package for autonomous driving vehicles
EP3552904B1 (en) Method, device and computer program product for predicting the development of a traffic scene involving several participants
WO2024137249A1 (en) Tracker trajectory validation
CN113415278B (zh) 用于使用周围车辆运动流跟随最近在径车辆的系统和过程

Legal Events

Date Code Title Description
AS Assignment

Owner name: FORD GLOBAL TECHNOLOGIES, LLC, MICHIGAN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:OLSON, EDWIN;GALCERAN, ENRIC;CUNNINGHAM, ALEXANDER G.;AND OTHERS;SIGNING DATES FROM 20150721 TO 20150728;REEL/FRAME:036225/0669

Owner name: THE REGENTS OF THE UNIVERSITY OF MICHIGAN, OFFICE

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:OLSON, EDWIN;GALCERAN, ENRIC;CUNNINGHAM, ALEXANDER G.;AND OTHERS;SIGNING DATES FROM 20150721 TO 20150728;REEL/FRAME:036225/0669

AS Assignment

Owner name: FORD GLOBAL TECHNOLOGIES, LLC, MICHIGAN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MCBRIDE, JAMES ROBERT;REEL/FRAME:036954/0719

Effective date: 20150727

Owner name: THE REGENTS OF THE UNIVERSITY OF MICHIGAN, MICHIGA

Free format text: CORRECTIVE ASSIGNMENT TO REMOVE THE ASSIGNOR JAMES ROBERT MCBRIDE DATA AND REMOVE THE FIRST RECEIVING PARTY DATA PREVIOUSLY RECORDED AT REEL: 036225 FRAME: 0669. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT;ASSIGNORS:CUNNINGHAM, ALEXANDER G.;EUSTICE, RYAN M.;GALCERAN, ENRIC;AND OTHERS;SIGNING DATES FROM 20150721 TO 20150728;REEL/FRAME:037043/0220

STCF Information on status: patent grant

Free format text: PATENTED CASE

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 4